<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
ms-8maps_nonalpha-ds
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 6.3278
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.6062 | 0.07 | 100 | 6.5287 |
| 6.5093 | 0.14 | 200 | 6.5134 |
| 6.5097 | 0.21 | 300 | 6.5029 |
| 6.5038 | 0.28 | 400 | 6.4878 |
| 6.4771 | 0.35 | 500 | 6.4600 |
| 6.4497 | 0.43 | 600 | 6.4419 |
| 6.442 | 0.5 | 700 | 6.4238 |
| 6.4188 | 0.57 | 800 | 6.3903 |
| 6.3898 | 0.64 | 900 | 6.3687 |
| 6.3575 | 0.71 | 1000 | 6.3503 |
| 6.3414 | 0.78 | 1100 | 6.3396 |
| 6.3417 | 0.85 | 1200 | 6.3329 |
| 6.332 | 0.92 | 1300 | 6.3284 |
| 6.3404 | 0.99 | 1400 | 6.3278 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
